Learning Action Models: Qualitative Approach
This work addresses a foundational problem in formal logic and AI for researchers in dynamic epistemic logic, but it is incremental as it builds on existing update methods.
The paper tackles the problem of learning action models from observations in dynamic epistemic logic, showing that deterministic actions are finitely identifiable while non-deterministic ones are identifiable in the limit, and introduces specific learning methods for deterministic actions.
In dynamic epistemic logic, actions are described using action models. In this paper we introduce a framework for studying learnability of action models from observations. We present first results concerning propositional action models. First we check two basic learnability criteria: finite identifiability (conclusively inferring the appropriate action model in finite time) and identifiability in the limit (inconclusive convergence to the right action model). We show that deterministic actions are finitely identifiable, while non-deterministic actions require more learning power-they are identifiable in the limit. We then move on to a particular learning method, which proceeds via restriction of a space of events within a learning-specific action model. This way of learning closely resembles the well-known update method from dynamic epistemic logic. We introduce several different learning methods suited for finite identifiability of particular types of deterministic actions.